Menu
CONVERSE TO LEARN
  • Overview
  • Projects
    • STEM
    • CA's as Reading Partners
    • AI At Scale
    • codeAI
  • Scholarship
  • Media
  • Team
  • Contact Us
  • Overview
  • Projects
    • STEM
    • CA's as Reading Partners
    • AI At Scale
    • codeAI
  • Scholarship
  • Media
  • Team
  • Contact Us

Research Projects

Picture

Conversational Technologies for Supporting STEM Discourse

In this line of research, we integrate conversational agents into STEM oriented television shows to allow children to directly speak with the show's main characters. The conversation is designed to prime children to engage in observation, prediction, pattern identification, and problem solving. ​

Conversational Agents as Reading Partners

In this project, we have designed a Conversational Agent (CA)-based audio story using Google’s voice-driven interface (Google Assistant). Our study confirmed that dialogue helps learning--children in both dialogue conditions (with a human partner or a conversational agent) learned more than those without dialogue.
Picture
Picture

Scalable Conversational AI for Literacy Development

The objective of this project is to ​evaluate the feasibility of using automatic question-answer (QA) generation to facilitate the learning and assessment of narrative comprehension skills, a critical component of reading proficiency. This innovation can enable large-scale, cost-effective development and production of learning and assessment resources.

Bilingual Interactive E-Books

This project is aimed to explore and examine new solutions to the challenges in improving bilingual home literacy practices for children in language minority and Foreign Language (EFL) settings. Using a design-based research methodology, this innovation – an interactive bilingual story e-book, has the potential to provide dialogic reading opportunities for parents whose first language is not English and thus promote English language development for those children.
Picture
Picture

Explainable AI and Trust

This series of studies aims to understand the psychological and social consequences of AI transparency. We are examining whether providing children and adults with information about how AI works affects their trust and parasocial relationships towards AI. Eventually, these studies will inform the development of curriculum to promote children’s AI literacy, which is crucial to help them use these technologies effectively and become less vulnerable to misinformation and bias.

Media Usage in Multicultural Families

We are partnering with PBS SoCal's Family Math Project to co-design a series of math-focused video programs accompanied by hands-on learning activities (e.g., crafting, art projects) that situate math learning within the cultural resources of a local Latino community, investigating how drawing on diverse groups’ “funds of knowledge” can promote parent-child joint STEM engagement. This research will provide critical evidence on a culturally responsive, media-enriched approach to early STEM learning that builds on the assets of marginalized communities.
Picture
Picture

Digital Reading in Early Childhood

This line of research focuses on how the design of interactive touchscreen storybooks supports or hinders children’s language learning. We examined the effectiveness of common design features (e.g., hotspots, audio narration) and identify developmentally appropriate techniques to improve the usability of e-book interface. This also includes the analysis of children’s e-reading behaviors through mining log data.
Proudly powered by Weebly